ABSTRACT
The use of automobiles has become an integral part of our current civilization, half of which are cars. With the introduction of autonomous driving in cars, there is a need for additional safety procedures to ensure the safety of the passengers.
In this direction, this work proposes a video-based accident recognition system for cars. The proposed approach uses video information available through dashboard cameras and deep learning to recognize if the vehicle had an accident. The effectiveness of the proposed approach is evaluated on a new video data set.
